{"total":68,"rows":[{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336,"area":"mllm"},{"id":"2302.12066","title":"Teaching CLIP to Count to Ten","created":"2023-02-23","cited_by_count":198,"area":"mllm"},{"id":"2411.16724","title":"Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens","created":"2024-11-23","cited_by_count":143,"area":"mllm"},{"id":"2410.02762","title":"Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations","created":"2024-10-03","cited_by_count":104,"area":"mllm"},{"id":"2304.05653","title":"A Closer Look at the Explainability of Contrastive Language-Image Pre-training","created":"2023-04-12","cited_by_count":96,"area":"mllm"},{"id":"2207.11514","title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models","created":"2022-07-23","cited_by_count":95,"area":"mllm"},{"id":"2405.20985","title":"DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models","created":"2024-05-31","cited_by_count":75,"area":"mllm"},{"id":"2411.17491","title":"What's in the Image? A Deep-Dive into the Vision of Vision Language Models","created":"2024-11-26","cited_by_count":68,"area":"mllm"},{"id":"2411.18620","title":"Cross-modal Information Flow in Multimodal Large Language Models","created":"2024-11-27","cited_by_count":67,"area":"mllm"},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2404.09654","title":"Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection","created":"2024-04-15","cited_by_count":36,"area":"mllm"},{"id":"2412.18108","title":"Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach","created":"2024-12-24","cited_by_count":35,"area":"mllm"},{"id":"2506.09047","title":"Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs","created":"2025-06-10","cited_by_count":35,"area":"mllm"},{"id":"2312.17174","title":"Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution","created":"2023-12-28","cited_by_count":34,"area":"mllm"},{"id":"2204.07441","title":"COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval","created":"2022-04-15","cited_by_count":33,"area":"mllm"},{"id":"2506.23270","title":"Token Activation Map to Visually Explain Multimodal LLMs","created":"2025-06-29","cited_by_count":32,"area":"mllm"},{"id":"2206.15462","title":"Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations","created":"2022-06-30","cited_by_count":24,"area":"mllm"},{"id":"2406.10995","title":"Concept-skill Transferability-based Data Selection for Large Vision-Language Models","created":"2024-06-16","cited_by_count":24,"area":"mllm"},{"id":"2411.18111","title":"When Large Vision-Language Models Meet Person Re-Identification","created":"2024-11-27","cited_by_count":15,"area":"mllm"},{"id":"2503.13891","title":"Where do Large Vision-Language Models Look at when Answering Questions?","created":"2025-03-18","cited_by_count":15,"area":"mllm"},{"id":"2407.14412","title":"DEAL: Disentangle and Localize Concept-level Explanations for VLMs","created":"2024-07-19","cited_by_count":14,"area":"mllm"},{"id":"2505.21472","title":"Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration","created":"2025-05-27","cited_by_count":11,"area":"mllm"},{"id":"2312.04231","title":"Adventures of Trustworthy Vision-Language Models: A Survey","created":"2023-12-07","cited_by_count":10,"area":"mllm"},{"id":"2502.18816","title":"Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP","created":"2025-02-26","cited_by_count":8,"area":"mllm"},{"id":"2312.17345","title":"3VL: Using Trees to Improve Vision-Language Models' Interpretability","created":"2023-12-28","cited_by_count":7,"area":"mllm"},{"id":"2408.13461","title":"Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach","created":"2024-08-24","cited_by_count":7,"area":"mllm"},{"id":"2411.04077","title":"H-POPE: Hierarchical Polling-based Probing Evaluation of Hallucinations in Large Vision-Language Models","created":"2024-11-06","cited_by_count":6,"area":"mllm"},{"id":"2505.10764","title":"SurgXBench: Explainable Vision-Language Model Benchmark for Surgery","created":"2025-05-16","cited_by_count":6,"area":"mllm"},{"id":"2507.10610","title":"LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents","created":"2025-07-13","cited_by_count":6,"area":"mllm"},{"id":"2508.05430","title":"Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions","created":"2025-08-07","cited_by_count":6,"area":"mllm"},{"id":"2511.17722","title":"Can Vision-Language Models Count? A Synthetic Benchmark and Analysis of Attention-Based Interventions","created":"2025-11-21","cited_by_count":6,"area":"mllm"},{"id":"2509.22415","title":"Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models","created":"2025-09-26","cited_by_count":5,"area":"mllm"},{"id":"2410.09382","title":"CLIP-SCGI: Synthesized Caption-Guided Inversion for Person Re-Identification","created":"2024-10-12","cited_by_count":4,"area":"mllm"},{"id":"2509.24072","title":"Uncovering Grounding IDs: How External Cues Shape Multimodal Binding","created":"2025-09-28","cited_by_count":4,"area":"mllm"},{"id":"2603.29676","title":"A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models","created":"2026-03-31","cited_by_count":4,"area":"mllm"},{"id":"2505.17812","title":"Seeing It or Not? Interpretable Vision-aware Latent Steering to Mitigate Object Hallucinations","created":"2025-05-23","cited_by_count":3,"area":"mllm"},{"id":"2511.12978","title":"Concept Regions Matter: Benchmarking CLIP with a New Cluster-Importance Approach","created":"2025-11-17","cited_by_count":3,"area":"mllm"},{"id":"2601.08151","title":"Where Does Vision Meet Language? Understanding and Refining Visual Fusion in MLLMs via Contrastive Attention","created":"2026-01-13","cited_by_count":3,"area":"mllm"},{"id":"2605.08200","title":"Where Reliability Lives in Vision-Language Models: A Mechanistic Study of Attention, Hidden States, and Causal Circuits","created":"2026-05-05","cited_by_count":3,"area":"mllm"},{"id":"2407.20034","title":"MaskInversion: Localized Embeddings via Optimization of Explainability Maps","created":"2024-07-29","cited_by_count":2,"area":"mllm"},{"id":"2412.13333","title":"Beyond Accuracy: On the Effects of Fine-tuning Towards Vision-Language Model's Prediction Rationality","created":"2024-12-17","cited_by_count":2,"area":"mllm"},{"id":"2412.18675","title":"TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models","created":"2024-12-24","cited_by_count":2,"area":"mllm"},{"id":"2506.01097","title":"Task-Related Token Compression in Multimodal Large Language Models from an Explainability Perspective","created":"2025-06-01","cited_by_count":2,"area":"mllm"},{"id":"2507.07731","title":"Energy-Guided Decoding for Object Hallucination Mitigation","created":"2025-07-10","cited_by_count":2,"area":"mllm"},{"id":"2509.18733","title":"Knowledge Transfer from Interaction Learning","created":"2025-09-23","cited_by_count":2,"area":"mllm"},{"id":"2603.23118","title":"SMSP: A Plug-and-Play Strategy of Multi-Scale Perception for MLLMs to Perceive Visual Illusions","created":"2026-03-24","cited_by_count":2,"area":"mllm"},{"id":"2605.24024","title":"Mitigating Hallucinations in Large Vision-Language Models via Causal Route Gating","created":"2026-05-20","cited_by_count":2,"area":"mllm"},{"id":"2408.09706","title":"MePT: Multi-Representation Guided Prompt Tuning for Vision-Language Model","created":"2024-08-19","cited_by_count":1,"area":"mllm"},{"id":"2503.15886","title":"Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance","created":"2025-03-20","cited_by_count":1,"area":"mllm"},{"id":"2508.14280","title":"Multi-Rationale Explainable Object Recognition via Contrastive Conditional Inference","created":"2025-08-19","cited_by_count":1,"area":"mllm"},{"id":"2509.06336","title":"Multi-View Slot Attention Using Paraphrased Texts for Face Anti-Spoofing","created":"2025-09-08","cited_by_count":1,"area":"mllm"},{"id":"2509.15243","title":"Multi-Modal Interpretability for Enhanced Localization in Vision-Language Models","created":"2025-09-17","cited_by_count":1,"area":"mllm"},{"id":"2603.06302","title":"DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models","created":"2026-03-06","cited_by_count":1,"area":"mllm"},{"id":"2604.13073","title":"OmniTrace: A Unified Framework for Generation-Time Attribution in Omni-Modal LLMs","created":"2026-03-20","cited_by_count":1,"area":"mllm"},{"id":"2605.07148","title":"Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models","created":"2026-05-08","cited_by_count":1,"area":"mllm"},{"id":"2605.09598","title":"SoccerLens: Grounded Soccer Video Understanding Beyond Accuracy","created":"2026-05-10","cited_by_count":1,"area":"mllm"},{"id":"2605.22168","title":"Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability","created":"2026-05-21","cited_by_count":1,"area":"mllm"},{"id":"2606.14758","title":"Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability","created":"2026-06-08","cited_by_count":1,"area":"mllm"},{"id":"2305.10434","title":"Learning the Visualness of Text Using Large Vision-Language Models","created":"2023-05-11","cited_by_count":0,"area":"mllm"},{"id":"2307.06795","title":"Leveraging Vision-Language Foundation Models for Fine-Grained Downstream Tasks","created":"2023-07-13","cited_by_count":0,"area":"mllm"},{"id":"2312.11570","title":"Understanding the Multi-modal Prompts of the Pre-trained Vision-Language Model","created":"2023-12-18","cited_by_count":0,"area":"mllm"},{"id":"2510.23253","title":"A Video Is Not Worth a Thousand Words","created":"2025-10-27","cited_by_count":0,"area":"mllm"},{"id":"2604.04473","title":"Beyond Standard Benchmarks: A Systematic Audit of Vision-Language Model's Robustness to Natural Semantic Variation Across Diverse Tasks","created":"2026-04-06","cited_by_count":0,"area":"mllm"},{"id":"2604.19083","title":"ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety","created":"2026-04-21","cited_by_count":0,"area":"mllm"},{"id":"2605.13047","title":"Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency","created":"2026-05-13","cited_by_count":0,"area":"mllm"},{"id":"2605.14750","title":"EVA: Editing for Versatile Alignment against Jailbreaks","created":"2026-05-14","cited_by_count":0,"area":"mllm"},{"id":"2609.17953","title":"EDCT-Bench: Uncovering Faithfulness Gaps in VLMs via Explanation-Driven Counterfactual Testing","created":"2026-09-16","cited_by_count":0,"area":"mllm"},{"id":"2610.14190","title":"Cross-Modal Latent Influence: Patch-Level Training Sample Attribution for Vision-Language Models","created":"2026-10-09","cited_by_count":0,"area":"mllm"}],"next_cursor":null}